perplexity-ai/r1-1776
Updated
•
7.75k
•
1.53k
Krum Arnaudov
krumeto
AI & ML interests
None yet
Recent Activity
liked
a model
5 days ago
perplexity-ai/r1-1776
liked
a model
10 days ago
NousResearch/DeepHermes-3-Llama-3-8B-Preview
liked
a model
about 1 month ago
jxm/cde-small-v2
Organizations
None yet
krumeto's activity
liked
a
model
5 days ago
liked
a
model
10 days ago
liked
a
model
about 1 month ago
reacted to
singhsidhukuldeep's
post with 👍
3 months ago
Post
1268
Exciting breakthrough in AI Recommendation Systems! Just read a fascinating paper from Meta AI and UW-Madison researchers on unifying generative and dense retrieval methods for recommendations.
The team introduced LIGER (LeveragIng dense retrieval for GEnerative Retrieval), a novel hybrid approach that combines the best of both worlds:
Key Technical Innovations:
- Integrates semantic ID-based generative retrieval with dense embedding methods
- Uses a T5 encoder-decoder architecture with 6 layers, 6 attention heads, and 128-dim embeddings
- Processes item attributes through sentence-T5-XXL for text representations
- Employs a dual-objective training approach combining cosine similarity and next-token prediction
- Implements beam search with size K for candidate generation
- Features an RQ-VAE with 3-layer MLP for semantic ID generation
Performance Highlights:
- Significantly outperforms traditional methods on cold-start recommendations
- Achieves state-of-the-art results on major benchmark datasets (Amazon Beauty, Sports, Toys, Steam)
- Reduces computational complexity from O(N) to O(tK) where t is semantic ID count
- Maintains minimal storage requirements while improving recommendation quality
The most impressive part? LIGER effectively solves the cold-start problem that has long plagued recommendation systems while maintaining computational efficiency.
This could be a game-changer for e-commerce platforms and content recommendation systems!
What are your thoughts on hybrid recommendation approaches?
The team introduced LIGER (LeveragIng dense retrieval for GEnerative Retrieval), a novel hybrid approach that combines the best of both worlds:
Key Technical Innovations:
- Integrates semantic ID-based generative retrieval with dense embedding methods
- Uses a T5 encoder-decoder architecture with 6 layers, 6 attention heads, and 128-dim embeddings
- Processes item attributes through sentence-T5-XXL for text representations
- Employs a dual-objective training approach combining cosine similarity and next-token prediction
- Implements beam search with size K for candidate generation
- Features an RQ-VAE with 3-layer MLP for semantic ID generation
Performance Highlights:
- Significantly outperforms traditional methods on cold-start recommendations
- Achieves state-of-the-art results on major benchmark datasets (Amazon Beauty, Sports, Toys, Steam)
- Reduces computational complexity from O(N) to O(tK) where t is semantic ID count
- Maintains minimal storage requirements while improving recommendation quality
The most impressive part? LIGER effectively solves the cold-start problem that has long plagued recommendation systems while maintaining computational efficiency.
This could be a game-changer for e-commerce platforms and content recommendation systems!
What are your thoughts on hybrid recommendation approaches?
Information about performance of different quantisation options
#1 opened 3 months ago
by
krumeto
liked
2
models
3 months ago
liked
a
model
5 months ago
liked
a
dataset
5 months ago
liked
a
model
5 months ago
updated
a
model
7 months ago
liked
a
model
7 months ago
liked
a
dataset
8 months ago
liked
2
models
9 months ago
Reason for `trust_remote_code`?
2
#7 opened 10 months ago
by
krumeto
liked
2
models
12 months ago
liked
2
models
about 1 year ago